Muse Wonder
Public AI IQ model profile with source-backed benchmark results and derived ranking context.
Muse Wonder API pricing — full price table, workload cost examples, and cheaper alternatives.
Release and Capabilities
| Public release | 2026-10-12 |
|---|---|
| Modalities | text, image, video, audio |
| Context window | 1,048,576 tokens |
Available through Meta Model API (muse-wonder-1.0, Standard mode) and Muse Code.
Publisher-reported capabilities
- Meta announced this distinct Muse Wonder series model on October 12, 2026.
- Designed for sustained coding and personal and professional agentic tasks.
Limitations and availability caveats
- Model weights are not publicly available.
- Muse Code Contributor mode is enabled by default; subscribers can disable it in settings.
Official release and model references
Measured Coverage and Estimates
Muse Wonder has 10 of 39 tracked IQ benchmark inputs across 4 of 7 dimensions. Raw benchmark tables contain source-backed results only. Derived IQ combines all six dimensions using the shared scoring methodology, including estimates where direct coverage is incomplete.
Among dimensions with direct benchmark coverage, this profile's highest estimated scores are Programmatic Reasoning (IQ 143) and Academic Reasoning (IQ 136). These dimension estimates can include statistical adjustments or predecessor priors; they are not raw benchmark percentages or claims of real-world task success.
Benchmark versions, evaluation harnesses, and coverage affect comparisons; a missing result is not a score of zero. See the scoring methodology for estimation and uncertainty limits.
IQ Dimensions
| Dimension | IQ | Coverage |
|---|---|---|
| Abstract Reasoning | 108 | 0/5 |
| Mathematical Reasoning | 122 | 0/5 |
| Academic Reasoning | 136 | 3/6 |
| Programmatic Reasoning | 143 | 1/6 |
| Computer Use | 122 | 0/5 |
| Reliability | 126 | 2/6 |
| Knowledge Work | 135 | 4/6 |
Benchmark Results
| Benchmark | Score | Dimension |
|---|---|---|
| AA-Briefcase v1.1 Elo | 1658.65 | Knowledge Work |
| AA Long Context Reasoning v1.1 | 80.6667 | Reliability |
| AA Omniscience | 25.4833 | Reliability |
| AutomationBench-AA | 68.0946 | Knowledge Work |
| CritPt | 28.2857 | Academic Reasoning |
| GDP.pdf | 30.6 | Knowledge Work |
| GDPval-AA v2.1 normalized score | 63.517 | Knowledge Work |
| Humanity's Last Exam | 50.0927 | Academic Reasoning |
| SciCode | 60.3009 | Academic Reasoning |
| Terminal-Bench 4.0 | 52.0202 | Programmatic Reasoning |
Compare
Frequently Asked Questions
- What is the IQ of Muse Wonder?
- Muse Wonder has an estimated IQ of 127, which ranks #21 out of 164 public models on the AI IQ leaderboard. The score combines seven equally weighted reasoning dimensions using measured benchmark results and conservative estimates for missing coverage.
- How much does Muse Wonder cost?
- Muse Wonder costs $4.00 per million input tokens and $20.00 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $30.41 per million input-plus-output tokens.
- Is Muse Wonder open source?
- No — Muse Wonder is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.
- When was Muse Wonder released?
- Muse Wonder was publicly released on October 12, 2026.
- How large is the context window of Muse Wonder?
- Muse Wonder supports a context window of 1,048,576 tokens — the amount of text it can consider in a single request.